1 day ago
Hyderābād, IndiaMid Level
Responsibilities
- Build AI-based anomaly-detection and monitoring systems using machine learning and statistical methods for large-scale data.
- Design, implement, test, deploy, operate, and tune online services, automation, and tooling across the software development lifecycle.
- Detect data-quality issues including missing or late feeds, volume and distribution shifts, schema and contract drift, duplication, and implausible clinical values.
- Develop and evaluate statistical, time-series, and machine-learning detection approaches using precision, recall, and alert usefulness.
- Create actionable alerts, root-cause context, data-quality metrics, and dashboards for engineering and clinical teams.
- Build quality checks into data-processing pipelines with data-processing engineers.
- Collaborate with product managers, clinical informaticists, architects, and engineers to define data quality standards.
- Participate in design reviews, code reviews, and on-call operations for owned services.
Requirements
- Bachelor’s degree in Computer Science or a related field, or equivalent practical experience.
- At least 1 year of experience building production-quality services on a cloud platform such as Azure, AWS, or GCP.
- At least 2 years of experience writing Python for machine learning, AI-based data analytics, or statistical modeling.
- Hands-on experience with software design, implementation, testing, deployment, operations, and performance.
- Working knowledge of statistics and model-evaluation methods.
- Strong problem-solving, communication, collaboration, and ability to learn a new domain quickly.
- Preferred experience with AI or machine-learning anomaly detection, statistical methods, time-series analysis, or data-quality monitoring.
- Preferred experience with distributed teams, especially across India and the United States.
- Preferred experience processing large datasets with Spark, Databricks, or comparable distributed frameworks, plus strong SQL.
- Preferred experience running services on Microsoft Azure.
- Preferred familiarity with Great Expectations, Deequ, Soda, or equivalent data-quality and observability frameworks.
- Preferred experience operating production machine-learning models, including drift monitoring and retraining.
- Preferred exposure to healthcare, clinical, or other regulated data.
Tech Stack
Categories
About Truveta
Truveta builds a health provider–led data platform that aggregates and de-identifies EHR data from U.S. health systems for research and clinical insights. It sells subscriptions and evidence-generation tools to life sciences companies, health systems, and researchers to support real-world data and regulatory-grade studies. Founded in 2020 and headquartered in the Seattle area, the company is privately held and backed by participating health systems.